Search results

(1 - 3 of 3)
NOVEL AUTONOMOUS DRONE ARCHITECTURE WITH WIRELESS NETWORK USING REAL-TIME SIGNAL PROCESSING AND MOBILE DEVICE FOR ASSISTING RESCUE SERVICE
Title
NOVEL AUTONOMOUS DRONE ARCHITECTURE WITH WIRELESS NETWORK USING REAL-TIME SIGNAL PROCESSING AND MOBILE DEVICE FOR ASSISTING RESCUE SERVICE
Creator
Kim, Heekyung
Date
2015, 2015-12
Description
The Autonomous Drone can be economically one of the effective and efficient tools for disaster management. In this research, for disaster...
Show moreThe Autonomous Drone can be economically one of the effective and efficient tools for disaster management. In this research, for disaster relief operations, Autonomous Drone Architecture with wireless network provides disaster assistance by tracking a survivor and getting important information from multiple sensors on it. [1] ADWN architecture consist of two different platforms, Raspberry pi and Arduino, to separate their roles of the process, which are like collecting the sensor data and sending control signal from Raspberry Pi to Arduino. Once gathering data from sensors and transmitting it to Raspberry Pi, it can analysis by applying signal processing formula in real-time. [2] In this case, Raspberry Pi can multitask process and use various language libraries such as OpenCV, Python, and others. Also, Raspberry Pi can add lots of sensors, a camera, and other kinds of boards. Using these features, transmitted data can be processed in real-time and be sending to Arduino to control with reduced error. These strength of ADWN architecture provides scalability and high availability to control drone as a disaster assistance.
M.S. in Electrical Engineering, December 2015
Show less
RECONFIGURABLE SYSTEM-ON.CHIP SOLUTION FOR ULTRASONIC IMAGING APPLICATIONS
Title
RECONFIGURABLE SYSTEM-ON.CHIP SOLUTION FOR ULTRASONIC IMAGING APPLICATIONS
Creator
Gal, Paul
Date
2015, 2015-12
Description
Ultrasonic system have evolved from a basic single transducer system to full arrays capable of 3-dimensional scans. These advanced systems are...
Show moreUltrasonic system have evolved from a basic single transducer system to full arrays capable of 3-dimensional scans. These advanced systems are design for specific applications and target materials. These systems need to be able to process the vast amount of data that is generated while maintaining portability a flexible and reconfigurable system. Specific hardware accelerators are built to perform ultrasonic signal processing quickly and efficiently. This system allows for a variety of parameters like signal lengths and processing characteristics to be reconfigurable to allow for flexibility for different applications. A system is developed to provide an effective storage and data transfer system which will allows researchers to quickly gather data. Specific compression and reconstruction algorithms are implemented as accelerators to increase the systems overall performance. For data transfer a simple Real Time Operating System and Ethernet connective is developed. This is all implemented on the ZEDBoard Zynq SoC for maximum flexibility and performance.Ultrasonic system have evolved from a basic single transducer system to full arrays capable of 3-dimensional scans. These advanced systems are design for specific applications and target materials. These systems need to be able to process the vast amount of data that is generated while maintaining portability a flexible and reconfigurable system. Specific hardware accelerators are built to perform ultrasonic signal processing quickly and efficiently. This system allows for a variety of parameters like signal lengths and processing characteristics to be reconfigurable to allow for flexibility for different applications. A system is developed to provide an effective storage and data transfer system which will allows researchers to quickly gather data. Specific compression and reconstruction algorithms are implemented as accelerators to increase the systems overall performance. For data transfer a simple Real Time Operating System and Ethernet connective is developed. This is all implemented on the ZEDBoard Zynq SoC for maximum flexibility and performance.Ultrasonic system have evolved from a basic single transducer system to full arrays capable of 3-dimensional scans. These advanced systems are design for specific applications and target materials. These systems need to be able to process the vast amount of data that is generated while maintaining portability a flexible and reconfigurable system. Specific hardware accelerators are built to perform ultrasonic signal processing quickly and efficiently. This system allows for a variety of parameters like signal lengths and processing characteristics to be reconfigurable to allow for flexibility for different applications. A system is developed to provide an effective storage and data transfer system which will allows researchers to quickly gather data. Specific compression and reconstruction algorithms are implemented as accelerators to increase the systems overall performance. For data transfer a simple Real Time Operating System and Ethernet connective is developed. This is all implemented on the ZEDBoard Zynq SoC for maximum flexibility and performance.
M.S. in Electrical Engineering, December 2015
Show less
AUTOMATION OF ULTRASONIC FLAW DETECTION APPLICATIONS USING DEEP LEARNING ALGORITHMS
Title
AUTOMATION OF ULTRASONIC FLAW DETECTION APPLICATIONS USING DEEP LEARNING ALGORITHMS
Creator
Virupakshappa, Kushal
Date
2021
Description
The Industrial Revolution-4.0 promises to integrate multiple technologies including but not limited to automation, cloud computing, robotics,...
Show moreThe Industrial Revolution-4.0 promises to integrate multiple technologies including but not limited to automation, cloud computing, robotics, and Artificial Intelligence. The non-Destructive Testing (NDT) industry has been shifting towards automation as well. For ultrasound-based NDT, these technological advancements facilitate smart systems hosting complex signal processing algorithms. Therefore, this thesis introduces the effective use of AI algorithms in challenging NDT scenarios. The first objective is to investigate and evaluate the performance of both supervised and unsupervised machine learning algorithms and optimize them for ultrasonic flaw detection utilizing Amplitude-scan (A-scan) data. Several inferences and optimization algorithms have been evaluated. It has been observed that proper choice of features for specific inference algorithms leads to accurate flaw detection. The second objective of this study is the hardware realization of the ultrasonic flaw detection algorithms on embedded systems. Support Vector Machine algorithm has been implemented on a Tegra K1 GPU platform and Supervised Machine Learning algorithms have been implemented on a Zynq FPGA for a comparative study. The third main objective is to introduce new deep learning architectures for more complex flaw detection applications including classification of flaw types and robust detection of multiple flaws in B-scan data. The proposed Deep Learning pipeline combines a novel grid-based localization architecture with meta-learning. This provides a generalized flaw detection solution wherein additional flaw types can be used for inference without retraining or changing the deep learning architecture. Results show that the proposed algorithm performs well in more complex scenarios with high clutter noise and the results are comparable with traditional CNN and achieve the goal of generality and robustness.
Show less